Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5134 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2657. Min Act: -0.0000

Data Index: 233758 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1498913 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1468874 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1415994 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2233. Min Act: -0.0000

Data Index: 845164 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2646. Min Act: -0.0000

Data Index: 156387 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2464. Min Act: -0.0000

Data Index: 419777 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1441333 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2359. Min Act: -0.0000

Data Index: 768316 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1145442 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1620145 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2358. Min Act: -0.0000

Data Index: 963677 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1160300 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2121. Min Act: -0.0000

Data Index: 263848 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2195. Min Act: -0.0000

Data Index: 486902 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2324. Min Act: -0.0000

Data Index: 569695 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2302. Min Act: -0.0000

Data Index: 371015 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1151881 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2203. Min Act: -0.0000

Data Index: 341843 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1038334 (C4 (Web Text))

Max Activating Token Index: 980